Triple

T23095300
Position Surface form Disambiguated ID Type / Status
Subject CECS E575869 entity
Predicate hasAbbreviation P43 FINISHED
Object CECS NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: CECS | Statement: [CECS, hasAbbreviation, CECS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CECS
Context triple: [CECS, hasAbbreviation, CECS]
  • A. CECS chosen
    CECS is the commonly used abbreviation for the College of Engineering and Computer Science, an academic division focused on engineering and computing disciplines.
  • B. CECAS
    CECAS is the College of Engineering, Computing and Applied Sciences at Clemson University, encompassing programs in engineering, computer science, and related applied disciplines.
  • C. MCECS
    MCECS is the Maseeh College of Engineering and Computer Science, an engineering and computing-focused academic college at Portland State University.
  • D. CEE
    CEE is the IATA airport code for Cherepovets Airport, a regional airport serving the city of Cherepovets in Russia.
  • E. CEE
    The CEE is the Spanish Episcopal Conference, the assembly of Catholic bishops in Spain that coordinates and represents the Church’s activities and positions in the country.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e245c060b48190a9bd61a47a16db17 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18de3b2b481909ef598b447ed4dd2 completed April 29, 2026, 4:49 a.m.
Created at: April 17, 2026, 3:57 p.m.